【Tensorflow+keras】解决Exception has occurred: ValueError Shape mismatch: The shape of labels (received

- 日理万妓 2022-10-05 04:52 28阅读 0赞

# 1 引言 #

使用网络做分类，训练的时候报错ValueError: Shape mismatch: The shape of labels (received (15,)) should equal the shape of logits except for the last dimension (received (5, 3))

from tensorflow.keras import datasets, layers, models
    
    IMG_WIDTH = 192
    IMG_HEIGHT = 192
    train_dir = 'train'
    validation_dir = 'validation'
    
    from google.colab import drive
    drive.mount('/content/drive')
    
    import os
    os.chdir("drive/My Drive/colab")
    
    from tensorflow.keras.preprocessing.image import ImageDataGenerator
    
    train_datagen = ImageDataGenerator(rescale=1./255)
    train_generator = train_datagen.flow_from_directory(
            train_dir,
            target_size=(IMG_WIDTH, IMG_HEIGHT),
            batch_size=5)
    
    validation_datagen = ImageDataGenerator(rescale=1./255)
    validation_generator = validation_datagen.flow_from_directory(
            validation_dir,
            target_size=(IMG_WIDTH, IMG_HEIGHT),
            batch_size=5)
    
    model = models.Sequential()
    model.add(layers.Conv2D(32, (3, 3), activation='relu',
                            input_shape=(IMG_WIDTH, IMG_HEIGHT, 3)))
    model.add(layers.MaxPooling2D((2, 2)))
    model.add(layers.Conv2D(64, (3, 3), activation='relu'))
    model.add(layers.MaxPooling2D((2, 2)))
    for i in range(2):
      model.add(layers.Conv2D(128, (3, 3), activation='relu'))
      model.add(layers.MaxPooling2D((2, 2)))
    
    model.add(layers.Flatten())
    model.add(layers.Dense(3, activation='softmax'))
    
    model.compile(optimizer='adam',
                  loss='sparse_categorical_crossentropy',
                  metrics=['accuracy'])
    
    history = model.fit_generator(
          train_generator,
          epochs=10,
          validation_data=validation_generator)

# 2 解决办法 #

原因是使用的损失函数，是sparse\_categorical\_crossentropy，在训练的时候会默认把label拉平，变成一维的，是有区别于categorical\_crossentropy的。  
要解决该问题就是更换损失函数为categorical\_crossentropy或者其他的损失函数

model.compile(optimizer='adam',
                  loss='categorical_crossentropy',
                  metrics=['accuracy'])